@inproceedings{zhu2015congestion,
author = {Zhu, Yibo and Zhu, Yibo and Eran, Haggai and Firestone, Daniel and Firestone, Daniel and Guo, Chuanxiong and Lipshteyn, Marina and Liron, Yehonatan and Padhye, Jitendra and Raindel, Shachar and Yahia, Mohamad Haj and Zhang, Ming and Padhye, Jitu},
title = {Congestion Control for Large-Scale RDMA Deployments},
booktitle = {SIGCOMM},
year = {2015},
month = {August},
abstract = {Modern datacenter applications demand high throughput (40Gbps) and ultra-low latency (< 10 microsecond per hop) from the network, with low CPU overhead. Standard TCP/IP stacks cannot meet these requirements, but Remote Direct Memory Access (RDMA) can. On IP-routed datacenter networks, RDMA is deployed using RoCEv2 protocol, which relies on Priority-based Flow Control (PFC) to enable a drop-free network. However, PFC can lead to poor application performance due to problems like head-of-line blocking and unfairness. To alleviates these problems, we introduce DCQCN, an end-to-end congestion control scheme for RoCEv2. To optimize DCQCN performance, we build a fluid model, and provide guidelines for tuning switch buffer thresholds, and other protocol parameters. Using a 3-tier Clos network testbed, we show that DCQCN dramatically improves throughput and fairness of RoCEv2 RDMA traffic. DCQCN is implemented in Mellanox NICs, and is being deployed in Microsoft’s datacenters.},
publisher = {ACM - Association for Computing Machinery},
url = {http://approjects.co.za/?big=en-us/research/publication/congestion-control-for-large-scale-rdma-deployments/},
edition = {SIGCOMM},
}